navidrome/model/lyrics_parse.go

92 lines
2.7 KiB
Go

package model
import (
"encoding/xml"
"fmt"
"slices"
"strings"
"github.com/navidrome/navidrome/log"
)
// lyricParser returns an empty list (not an error) when the input is not its
// format, so parsers can be tried in order. lang is the default for formats that
// do not carry their own.
type lyricParser func(lang string, contents []byte) (LyricList, error)
func parseLyricsfileBytes(_ string, contents []byte) (LyricList, error) {
return parseLyricsfile(string(contents))
}
// lyricFormats is the structured formats in content-sniff probe order; each
// row's suffixes drive sidecar dispatch. LRC/plain is the unlisted fallback floor.
var lyricFormats = []struct {
suffixes []string
parse lyricParser
}{
{[]string{".ttml"}, parseTTMLWithDefaultLang},
{[]string{".srt"}, parseSRTWithLanguage},
{[]string{".yaml", ".yml"}, parseLyricsfileBytes},
}
// ParseLyrics is the single entry point for parsing lyrics. A known suffix routes
// to that format's parser; an empty or "auto" suffix content-sniffs. Either way,
// a structured parser that does not match falls back to the LRC/plain-text floor.
func ParseLyrics(suffix, lang string, contents []byte) (LyricList, error) {
contents = stripBOM(contents)
if suffix == "" || strings.EqualFold(suffix, "auto") {
candidates := make([]lyricParser, len(lyricFormats))
for i, f := range lyricFormats {
candidates[i] = f.parse
}
return parseFirstMatch(lang, contents, candidates...)
}
for _, f := range lyricFormats {
if slices.ContainsFunc(f.suffixes, func(s string) bool { return strings.EqualFold(s, suffix) }) {
return parseFirstMatch(lang, contents, f.parse)
}
}
return plainLRC(lang, contents)
}
func parseFirstMatch(lang string, contents []byte, candidates ...lyricParser) (LyricList, error) {
for _, parse := range candidates {
list, err := parse(lang, contents)
if err == nil && len(list) > 0 {
return list, nil
}
if err != nil {
log.Warn("Error parsing lyrics, falling back to plain text", "error", err)
}
}
return plainLRC(lang, contents)
}
func plainLRC(lang string, contents []byte) (LyricList, error) {
lyric, err := parseLRC(lang, string(contents))
if err != nil {
return nil, fmt.Errorf("parsing lyrics: %w", err)
}
if lyric == nil || lyric.IsEmpty() {
return nil, nil
}
return LyricList{*lyric}, nil
}
func stripBOM(contents []byte) []byte {
return []byte(strings.TrimPrefix(string(contents), "\ufeff"))
}
func isTTMLDocument(text string) bool {
decoder := xml.NewDecoder(strings.NewReader(strings.TrimSpace(text)))
for {
token, err := decoder.Token()
if err != nil {
return false
}
if start, ok := token.(xml.StartElement); ok {
return strings.EqualFold(start.Name.Local, "tt")
}
}
}